基于内容与行为数据集成建模的企业微博粉丝兴趣挖掘方法
|
摘要
精准有效的微博营销需要准确了解粉丝的兴趣。本文主要目标是将微博内容分析与粉丝行为数据结合,从而更准确的发现并分析粉丝的兴趣。研究中主要应用超网络模型,通过构建话题超网络模型(FISN)对文本内容及行为数据进行集成建模。采用文本挖掘方法对微博内容进行分析,应用粉丝行为数据计算话题关注度,并构建了关键词的粉丝兴趣指数。以中移动官方微博为实例,基于FISN模型进行网络分析,可识别粉丝兴趣热点词、粉丝兴趣中心词、粉丝兴趣类团、粉丝兴趣热点类团等。通过密度矩阵及像矩阵分析,可以发现并识别各类团之间的联动关系。本研究的创新之处在于提出一种结合内容和行为数据的粉丝兴趣分析方法,可帮助企业更准确的了解用户兴趣,为改进其微博营销策略提供了有价值的参考。
The full understanding of fan's interest to microblog topics is of great importance to the effective microblog marketing.Aiming to get the fan's interest,we construct a fans-microblog interactive supernetwork model(FISN)in this paper by integrating the topics of microblog,keywords of contents and the interactivities of fans.The topic of fans interest is measured by an index which considers the main factors of interactivities including the topic remarks,forwarding and the quantities of participants.In the end,a case study on the Microblog of China Mobile Co.is conducted,in which the FISN model and fans' interests index are applied to analyze the focused topics,hot words and the related fans.The result shows good effects,suggested model and methods also provide an effective tool for enterprises to promote their microblog marketing policies.
The full understanding of fan's interest to microblog topics is of great importance to the effective microblog marketing.Aiming to get the fan's interest,we construct a fans-microblog interactive supernetwork model(FISN)in this paper by integrating the topics of microblog,keywords of contents and the interactivities of fans.The topic of fans interest is measured by an index which considers the main factors of interactivities including the topic remarks,forwarding and the quantities of participants.In the end,a case study on the Microblog of China Mobile Co.is conducted,in which the FISN model and fans' interests index are applied to analyze the focused topics,hot words and the related fans.The result shows good effects,suggested model and methods also provide an effective tool for enterprises to promote their microblog marketing policies.
引文
[1]Social media advertising value[J].William VanTien Dao,Angelina Nhat Hanh Le,Julian Ming-Sung Cheng,Der Chao Chen.International Journal of Advertising.2014(2).
[2]曾金,陆伟,陈海华,贺国秀.基于多模数据的微博用户兴趣识别研究[J].情报科学,2018,36(01):124-129.
[3]Yuto Yamaguchi,Toshiyuki Amagasa,Hiroyuki Kitagawa.Tag-based User Topic Discovery Using Twitter Lists[C].Proceedings of the 2011International Conference on Advances in Social Networks Analysis and Mining 2011:13-20.
[4]W Wu,B Zhang,M Ostendorf.Automatic generation of personalized annotation tags for twitter users[C].The 2010Annual Conference of the North A-merican Chapter of the Association for Computational Linguistics 2010:689-692.
[5]康海潇.基于标签的微博用户兴趣发现算法研究及应用[M].浙江大学硕士学位论文,2016,2-3.
[6]熊才伟,曹亚男.基于发文内容的微博用户兴趣挖掘方法研究[J].计算机应用研究,2018,35(06):1619-1623.
[7]J Chen,R Nairn,L Nelson,M Bernstein,E Chi.Short and tweet:experiments on recommending content from information streams[C].Proceedings of the 28th international conference on Human factors in computing systems 2010:1185-1194.
[8]J Weng,E P Lim,J Jiang,Q He.Twitter Rank:finding topic-sensitive influential twitterers[C].Proceedings of the third ACM international conference on Web search and data mining 2010:261-270.
[9]Wang T,Liu H,He J,et al.Mining user interests from information sharing behaviors in social media.Pacific-Asia Conference on Knowledge Discovery and Data Mining.2013.
[10]何必菲.基于微博用户行为的兴趣模型构建和可视化方法研究[M],哈尔滨工业大学硕士学位论文,2013:6-7.
[11]王永贵,张丰田,刘雨诗,肖成龙.微博中结合转发特性的用户兴趣话题挖掘方法[J].计算机应用研究,2017,34(07):2068-2071.
[12]邱云飞,王琳颍,邵良杉,郭红梅.基于微博短文本的用户兴趣建模方法.计算机工程,2014(12),40(2):275-279
[13]Liu Z,Chen X,Sun M.Mining the interests of Chinese microbloggers via keyword extraction.Frontiers of Computer Science in China.2012,1(6):76-87.
[14]D.M.Blei,A.Y.Ng,and M.I.Jordan,―Latent Dirichlet allocation,‖J.Mach.Learn.Res.,vol.3,pp.993-1022,Mar.2003.
[15]ZHIHENG X,Ru L,XIANG L,et al.Discovering User Interest on Twitter with a Modified AuthorTopic Model[C]//Proceedings of the 2011IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology Volume O1.2011.Washington,DC,USA:IEEE Computer Society,WI-IAT 11.
[16]杨仁凤,陈端兵,谢文波.微博用户兴趣主题抽取方法[J].电子科技大学学报,2018,47(04):633-640.
[17]陈文涛,张小明,等.构建微博用户兴趣模型的主题模型的分析[J].计算机科学,2013,40(4):127-135.
[18]刘永利,欧阳元新,闻佳.基于概念聚类的用户兴趣建模方法[J].北京航空航天大学学报,2010(2):188-192.
[19]张俊林.标签传播算法在微博用户兴趣图谱的应用[J].程序员,2012(7):50-53.
[20]Urban Transportation Network:Equilibrium Analysis with Mathematical Programming Methods.Sheffi Yosef..1985.
[21]Nagurney A.,Dong J.Supernetworks:DecisionMaking for the Information Age.Cheltenham:Edward Elgar Publishing,2002.
[22]Wu K.,Xi Y.J.,Liao X.,et al.Analysis on Current Research of Supernetwork Through Knowledge Mapping Method[A].Proceedings of International Conference on Knowledge Science,Engineering and Management,6th,KSEM,2013,538-550.
[23]王众托,王志平.超网络初探[J].管理学报,2008,5(l):1-8.
[24]王众托.关于超网络的一点思考[J].上海理工大学学报,2011,33(3):229-237.
[25]王志平,周生宝,郭俊芳,王众托.基于变分不等式的网络广告资源分配的超网络模型[J].大连海事大学学报,2007(33):69-72.
[26]曹杰,朱莉.考虑决策偏好的城市群应急协调超网络模型[J].管理科学学报,2014,17(11):33-42.
[27]吴义生,吴顺祥,白少布,朱振涛.面向网购的低碳供应链超网络优化模型及其应用[J].中国管理科学,2017,25(06):111-120.
[28]倪子建,荣莉莉,刘泉.基于超网络的维基百科内容知识本体演化研究[J].管理科学学报,2013,16(12):68-78.
[29]李纲,巴志超.科研合作超网络下的知识扩散演化模型研究[J].情报学报,2017,36(03):274-284.
[30]余谦,刘嘉玲.技术邻近动态下创新超网络的演化机理研究[J].科学学研究,2018,36(05):946-954.
[31]席运江,党延忠,廖开际.组织知识系统的知识超网络模型及应用[J].管理科学学报,2009,03:12-21.
[32]于洋.组织知识管理中的知识超网络研究[D],2009年6月.
[33]潘旭伟,汪雅喜,杨祎.知识超网络环境中集成优化过程的知识共享服务研究[J].科研管理,2011,32(05):87-93.
[34]张海红,吴文清.孵化器内创业者知识超网络涌现研究[J].管理学报,2017,14(05):695-703.
[35]尚艳超,王恒山,王艳灵.基于微博上信息传播的超网络模型[J].技术与创新管理,2012(3):175-178.
[36]安兴茹.基于正态分布的词频分析法高频词阈值研究[J].情报杂志,2014,10(33):129-136.
[37]Borgatti S P,Everett M G,Freeman L C.Ucinet for Windows:Software for Social Network Analysis[M].Harvard:Analytic Technologies,2002.
[2]曾金,陆伟,陈海华,贺国秀.基于多模数据的微博用户兴趣识别研究[J].情报科学,2018,36(01):124-129.
[3]Yuto Yamaguchi,Toshiyuki Amagasa,Hiroyuki Kitagawa.Tag-based User Topic Discovery Using Twitter Lists[C].Proceedings of the 2011International Conference on Advances in Social Networks Analysis and Mining 2011:13-20.
[4]W Wu,B Zhang,M Ostendorf.Automatic generation of personalized annotation tags for twitter users[C].The 2010Annual Conference of the North A-merican Chapter of the Association for Computational Linguistics 2010:689-692.
[5]康海潇.基于标签的微博用户兴趣发现算法研究及应用[M].浙江大学硕士学位论文,2016,2-3.
[6]熊才伟,曹亚男.基于发文内容的微博用户兴趣挖掘方法研究[J].计算机应用研究,2018,35(06):1619-1623.
[7]J Chen,R Nairn,L Nelson,M Bernstein,E Chi.Short and tweet:experiments on recommending content from information streams[C].Proceedings of the 28th international conference on Human factors in computing systems 2010:1185-1194.
[8]J Weng,E P Lim,J Jiang,Q He.Twitter Rank:finding topic-sensitive influential twitterers[C].Proceedings of the third ACM international conference on Web search and data mining 2010:261-270.
[9]Wang T,Liu H,He J,et al.Mining user interests from information sharing behaviors in social media.Pacific-Asia Conference on Knowledge Discovery and Data Mining.2013.
[10]何必菲.基于微博用户行为的兴趣模型构建和可视化方法研究[M],哈尔滨工业大学硕士学位论文,2013:6-7.
[11]王永贵,张丰田,刘雨诗,肖成龙.微博中结合转发特性的用户兴趣话题挖掘方法[J].计算机应用研究,2017,34(07):2068-2071.
[12]邱云飞,王琳颍,邵良杉,郭红梅.基于微博短文本的用户兴趣建模方法.计算机工程,2014(12),40(2):275-279
[13]Liu Z,Chen X,Sun M.Mining the interests of Chinese microbloggers via keyword extraction.Frontiers of Computer Science in China.2012,1(6):76-87.
[14]D.M.Blei,A.Y.Ng,and M.I.Jordan,―Latent Dirichlet allocation,‖J.Mach.Learn.Res.,vol.3,pp.993-1022,Mar.2003.
[15]ZHIHENG X,Ru L,XIANG L,et al.Discovering User Interest on Twitter with a Modified AuthorTopic Model[C]//Proceedings of the 2011IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology Volume O1.2011.Washington,DC,USA:IEEE Computer Society,WI-IAT 11.
[16]杨仁凤,陈端兵,谢文波.微博用户兴趣主题抽取方法[J].电子科技大学学报,2018,47(04):633-640.
[17]陈文涛,张小明,等.构建微博用户兴趣模型的主题模型的分析[J].计算机科学,2013,40(4):127-135.
[18]刘永利,欧阳元新,闻佳.基于概念聚类的用户兴趣建模方法[J].北京航空航天大学学报,2010(2):188-192.
[19]张俊林.标签传播算法在微博用户兴趣图谱的应用[J].程序员,2012(7):50-53.
[20]Urban Transportation Network:Equilibrium Analysis with Mathematical Programming Methods.Sheffi Yosef..1985.
[21]Nagurney A.,Dong J.Supernetworks:DecisionMaking for the Information Age.Cheltenham:Edward Elgar Publishing,2002.
[22]Wu K.,Xi Y.J.,Liao X.,et al.Analysis on Current Research of Supernetwork Through Knowledge Mapping Method[A].Proceedings of International Conference on Knowledge Science,Engineering and Management,6th,KSEM,2013,538-550.
[23]王众托,王志平.超网络初探[J].管理学报,2008,5(l):1-8.
[24]王众托.关于超网络的一点思考[J].上海理工大学学报,2011,33(3):229-237.
[25]王志平,周生宝,郭俊芳,王众托.基于变分不等式的网络广告资源分配的超网络模型[J].大连海事大学学报,2007(33):69-72.
[26]曹杰,朱莉.考虑决策偏好的城市群应急协调超网络模型[J].管理科学学报,2014,17(11):33-42.
[27]吴义生,吴顺祥,白少布,朱振涛.面向网购的低碳供应链超网络优化模型及其应用[J].中国管理科学,2017,25(06):111-120.
[28]倪子建,荣莉莉,刘泉.基于超网络的维基百科内容知识本体演化研究[J].管理科学学报,2013,16(12):68-78.
[29]李纲,巴志超.科研合作超网络下的知识扩散演化模型研究[J].情报学报,2017,36(03):274-284.
[30]余谦,刘嘉玲.技术邻近动态下创新超网络的演化机理研究[J].科学学研究,2018,36(05):946-954.
[31]席运江,党延忠,廖开际.组织知识系统的知识超网络模型及应用[J].管理科学学报,2009,03:12-21.
[32]于洋.组织知识管理中的知识超网络研究[D],2009年6月.
[33]潘旭伟,汪雅喜,杨祎.知识超网络环境中集成优化过程的知识共享服务研究[J].科研管理,2011,32(05):87-93.
[34]张海红,吴文清.孵化器内创业者知识超网络涌现研究[J].管理学报,2017,14(05):695-703.
[35]尚艳超,王恒山,王艳灵.基于微博上信息传播的超网络模型[J].技术与创新管理,2012(3):175-178.
[36]安兴茹.基于正态分布的词频分析法高频词阈值研究[J].情报杂志,2014,10(33):129-136.
[37]Borgatti S P,Everett M G,Freeman L C.Ucinet for Windows:Software for Social Network Analysis[M].Harvard:Analytic Technologies,2002.